|
![]() |
|
Please download the latest version of the Regression model in Excel
The material included in this web page is a part from our project on modeling the Life Table Data sets for various countries by using Stochastic Modeling Techniques and especially the First Exit Time Distribution for a stochastic process which models the Health State of a Population. The advantages of using the stochastic theory are:
The first modeling approach based on the hitting time or first exit time theory for a stochastic process was developed by: Janssen, J. and Skiadas, C. H., Dynamic Modelling of Life-Table Data. Applied Stochastic Models and Data Analysis, vol. 11, No 1, 35-49, 1995. The paper can be downloaded at:http://onlinelibrary.wiley.com/doi/10.1002/asm.3150110106/abstract. The paper was also presented at a meeting in Brussels (1995) celebrating the 100 years of the Association Royale des Actuaires Belges. The model proposed in the first paper of 1995 is a 5 parameter first exit time model. The model was applied to the mortality data of Belgium and France and stochastic simulations where done along with the nonlinear estimation of the model's parameters. The last five years we are working in simpler but yet quite powerful models to develop the distribution of the deaths per age in a large population or a country. The more successful models are presented and applied in the following. The nonlinear regression analysis technique used appears in this website along with easy to use Excel programs. The data used are from the Human Mortality Database, HMD (www.mortality.org ) The models are the First Exit Time Models The simpler model termed as "First Exit Time Model" is applied in recent years to life table data when the infant mortality is low. This model is included in the paper proposed by: Skiadas, C. H. and Skiadas, C., A Modeling Approach to Life Table Data Sets, in Recent Advances in Stochastic Modeling and Data Analysis, World Scientific, 350 - 359, 2007 g(t)=kt-3/2exp(-(l-(bt)c)2/(2t)) The second model termed as "First Exit Time IM" models quite well the Infant Mortality and is here applied to the 1960 data for various countries when these data sets are available. This model is included in the paper proposed by: Skiadas, C. and Skiadas, C. H., Development, Simulation and Application of First Exit Time Densities to Life Table Data, Communications in Statistics - Theory and Methods, Volume 39, Issue 3 January 2010, pages 444 - 451. This paper can be downloaded from: http://www.informaworld.com/smpp/content~db=all~content=a918382403~frm=titlelink The equation applied is: g(t)=kt-3/2(l+(c-1)(bt)c)exp(-(l-(bt)c)2/(2t))
The next Table summarizes the application results.
The applications include the Nonlinear Regression Analysis Program in Excel and you may download it and apply more data from the Human Mortality Database at: www.mortality.org |
||||
|
![]() |
|
|